Search Results for "llm"

garak checks if an LLM can be made to fail in a way we don't want. garak probes for hallucination, data leakage, prompt injection, misinformation, toxicity generation, jailbreaks, and many other weaknesses. garak's a free tool, we love developing it and are always interested in adding functionality to support applications. garak is a command-line tool, it's developed in Linux and OSX.

...The project focuses on detecting vulnerabilities, malicious behavior, and risky patterns that may be hidden inside skill files. It combines fast static checks with optional LLM-based semantic review for issues that require deeper intent analysis. It supports several input types, including Git repositories, URLs, zip files, folders, and individual files. It also produces practical reports with risk scores, severity labels, and recommendations that make security reviews easier to act on.

Robin is an AI-powered open source tool designed to assist investigators and researchers in conducting dark web OSINT (Open Source Intelligence) investigations. It combines automated dark web search capabilities with large language models (LLMs) to analyze and summarize information discovered across hidden services and Tor-based search engines. The tool helps refine investigative queries, collect results from multiple dark web sources, and filter relevant intelligence using AI-driven...

Stop shipping unsafe AI output. Local-first verification, safety monitoring, and guardrails for any LLM 100% Local | No Telemetry | Privacy-First | 500 free calls/day Links Product Page: subodhkc.com/products/llmverify npm: npmjs.com/package/llmverify GitHub: github.com/subodhkc/llmverify-npm Python Package (PyPI): github.com/subodhkc/llmverify Author: Subodh KC — AI governance, compliance, and security leader Feature One-liner What it catches Verify output await verify(aiResponse) Hallucinations, harmful content, quality issues Block injections isInputSafe(userMessage) Prompt injection, jailbreaks, malicious input Redact PII redactPII(text) Emails, phones, SSNs, credit cards, API keys Fix broken JSON repairJSON(broken) Missing brackets, trailing commas, unquoted keys Monitor health monitorLLM(client) Latency spikes, token drift, behavioral changes Sentinel tests sentinel.quick(client, model) LLM regressions b